Банк вопросов из реальных собеседований

In a casino product, the sales team needs to understand as early as possible whether the new player will become a VIP in terms of deposits and turnover. How to formulate a ML-task, target, forecast horizon and business action?

The product has a database of articles. The user can see hints or ask a free question. How to separate these two modes in search design?

Fairmarkit is a marketplace for corporate procurement: the customer creates a request, and the system suggests suitable suppliers. How to formulate the ML-problem of supplier selection before choosing a model?

If a user has added a ring, should the cart recommend more rings? How would you define the objective and category constraints?

You mentioned seasonality. How to work with it in features for recommendation systems, forecasts or product analytics?

The user sees a delivery fee or free-delivery threshold while building the cart. How should the system recompute it without surprising the user at checkout?

What does the language model get at the input, what returns at one step, and how does the sequence of response come from it?

After basic latency questions, the interviewer asks: what other anomalies can be noticed in the market-data file?

After launching the MVP, what events and features need to be collected to train the user-video ranking model?

What are the typical problems of recommendation systems and how can they be measured or reduced?

Which catalog features do cart recommendations need, and which data-quality problems should you expect in the product taxonomy?

Why reduce the accuracy of language model weights and activations, what quantization options exist, and what losses should be measured?

The company gave annual guidance for production growth. Why is it dangerous to spread it evenly across neighborhoods?

How to choose between improving the instruction, searching for knowledge, and training the model, including the LoRA adapters?

When would you choose a columnar database over Redis, MongoDB or a row-oriented relational database for ML/data pipelines?

When should you use a classic batch ETL and when is streaming for recommendations, analytics or ML features?

Search has embeddings and a full-text index. When to use both approaches and how to combine them?

The product has a search for documents/model files. When to use full-text, when to use vector search, and why might you need hybrid retrieval?

How to use location and image quality in a price or recommendation model without mixing product condition with photo quality?

How to evaluate the quality of search or RAG-system offline and online?

Which offline, online, and guardrail metrics would you use for an A/B test of dynamic delivery pricing?

We design ML for search on the marketplace. What business, online and offline metrics to choose?

What metrics should you use in a marketplace where clicks, contacts, deals, and distribution of impressions between sellers reflect different goals?

Which offline, online, and guardrail metrics would you use for cart recommendations when a click does not necessarily lead to a purchase?